University of Cambridge > Talks.cam > CUED Control Group Seminars > Toward Scalable Neuromorphic Control: From Conductance Modelling to Hierarchical Event-Based Architectures

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Toward Scalable Neuromorphic Control: From Conductance Modelling to Hierarchical Event-Based Architectures

Download to your calendar using vCal

If you have a question about this talk, please contact Rodolphe Sepulchre .

This seminar summarises PhD research that develops a methodology for scalable neuromorphic control, linking the modelling of individual neuromorphic elements to the design of large event-based control networks. At the element level, it introduces a kernel-based framework for learning fading-memory conductance dynamics from data while preserving causality, memristive structure, and time-scale separation. At the network level, it develops rebound Winner-Take-All motifs that unify rhythmic generation and discrete decision-making in a hierarchical architecture. The framework is demonstrated through a neuromorphic controller for a snake robot with layers for actuation, coordination, and supervisory switching.

This talk is part of the CUED Control Group Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Cambridge Usability Group Rdxhd Are You Interested In Learning About Blockchains?

Other talks

Title abstract tbc Not-so-noble gases, key tracers of Earth’s habitability: what their behaviour in planetary interiors can tell us? Non-stationarity in structural dynamics, challenges and implications for modelling and structural health monitoring John Kendrew Lecture - Title TBC Title to be confirmed TBC
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity